© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13922
    Prev
    Next
    INDEX
    Explanations

    government, taxis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rosh
    -1.01
    ArrowToggle
    -0.68
    aarrggbb
    -0.68
    MigrationBuilder
    -0.68
     AspNetCore
    -0.57
    webElementXpaths
    -0.55
    bootstrapcdn
    -0.54
    ➟
    -0.54
    veda
    -0.54
     ويكيپيديا
    -0.52
    POSITIVE LOGITS
     متعلقه
    0.71
    findpost
    0.60
    JsonFormat
    0.57
    
    0.56
    tvguidetime
    0.55
    хьтан
    0.54
     noDo
    0.52
     Adnan
    0.50
     JAXBElement
    0.50
     nakalista
    0.47
    Activations Density 0.127%

    No Known Activations